A recent study in The Lancet Oncology showed that AI found 20 percent more cancers on mammogram screens than radiologists alone.
Published in The Lancet Oncology, the study analyzed the scans of 80,000 Swedish women with a moderate hereditary risk of breast cancer who had undergone a mammogram between April 2021 and July 2022. Half of these scans were read by AI and then a radiologist to double-check the findings. The second group of scans was read by two researchers without the help of AI. (Currently, the standard of care across Europe is to have two radiologists analyze a scan before diagnosing a patient with breast cancer.)
The study showed that the AI group detected cancer in 6 out of every 1,000 scans, while the radiologists detected cancer in 5 per 1,000 scans. In other words, AI found 20 percent more cancers than the highly-trained radiologists.
Scientists have been using MRI images (like the ones pictured here) to train artificial intelligence to detect cancers earlier and with more accuracy. Here, MIT's AI system, MIRAI, looks for patterns in a patient's mammograms to detect breast cancer earlier than ever before. news.mit.edu
But even though the AI was better able to pinpoint cancer on an image, it doesn’t mean radiologists will soon be out of a job. Dr. Laura Heacock, a breast radiologist at NYU, said in an interview with CNN that radiologists do much more than simply screening mammograms, and that even well-trained technology can make errors. “These tools work best when paired with highly-trained radiologists who make the final call on your mammogram. Think of it as a tool like a stethoscope for a cardiologist.”
AI is still an emerging technology, but more and more doctors are using them to detect different cancers. For example, researchers at MIT have developed a program called MIRAI, which looks at patterns in patient mammograms across a series of scans and uses an algorithm to model a patient's risk of developing breast cancer over time. The program was "trained" with more than 200,000 breast imaging scans from Massachusetts General Hospital and has been tested on over 100,000 women in different hospitals across the world. According to MIT, MIRAI "has been shown to be more accurate in predicting the risk for developing breast cancer in the short term (over a 3-year period) compared to traditional tools." It has also been able to detect breast cancer up to five years before a patient receives a diagnosis.
The challenges for cancer-detecting AI tools now is not just accuracy. AI tools are also being challenged to perform consistently well across different ages, races, and breast density profiles, particularly given the increased risks that different women face. For example, Black women are 42 percent more likely than white women to die from breast cancer, despite having nearly the same rates of breast cancer as white women. Recently, an FDA-approved AI device for screening breast cancer has come under fire for wrongly detecting cancer in Black patients significantly more often than white patients.
As AI technology improves, radiologists will be able to accurately scan a more diverse set of patients at a larger volume than ever before, potentially saving more lives than ever.
ECOTEK students Noah Harris, 8, and Amir Muhammad, 10, doing measurements for their wind turbine project.
When Keith Young was a young father shepherding his three children through the Detroit public school system, he felt something was missing.
The students are working on issues ranging from robotics to 3D printing to finding a cure for a rare form of cancer.
"What I'd observed was a gap between the resources that were being offered to university-level folks and in the professional ranks compared to what had been offered to kids in K-12, and in particular, the ones that were in urban and rural communities," he recalls. "There was always a Boys and Girls Camp, always a YMCA. There was never a YMCA for scientists."
Thus, the concept of ECOTEK Lab was born. Young's vision was to narrow that gap -- by financing pop-up labs for students who want to find a scientific solution to hard-to-solve problems that can be found in their own backyards.
He began in 2005, guiding his own children through foundational experiments for eventual startup companies, focusing on climate change, DNA, making biofuels and other fields of research. In addition to the labs, Young says ECOTEK has also reached young people by way of field trips, science fairs, and in-class demonstrations at schools. Young considers himself a venture capitalist, lending resources to kid and teen scientists.
Keith Young, foreground, is the founder of ECOTEK. Behind him, from left, are his daughter, Amber, son, Keith Jr., and ECOTEK students Emmanuel Jefferson and Antoine Crews.
(Courtesy Young)
In 2008, he took a group of six students from Detroit who had been researching brownfields, or previously developed land that's now vacant, and how they affect climate change; their work culminated in a research trip to Cape Town, South Africa, and participation in a conference there.
Today, he's helping transform the lives of around 250 student scientists across the country in places like Detroit, Florida and Maryland. Those students are working on issues ranging from robotics to 3D printing to finding a cure for a rare form of cancer.
Participating students do not receive a grade -- "they have to have passion to do the work." To take part, students must complete an application process and pay a small fee to use the lab, which is based on family resources, Young says. Students usually work in groups of two to three and are matched with a STEM mentor who can help when they run into research roadblocks.
In one lab in Detroit, a trio of teens is working to develop battery technology for smart mobility along with microbial fuel cells. In another lab, students focus on plant-based drug discovery. One of their projects is using plant DNA to better understand how the breast cancer gene mutation called BRCA1 works in the human body. In the African American population, about 35 percent of women with triple-negative breast cancer test positive for this mutation, and they usually don't learn of their diagnosis until the cancer has spread.
ECOTEK students have also had a slightly larger audience – the United Nations.
A third Detroit-based lab is led by Keith Young's daughter and one of ECOTEK's original students: Founder Briana Young, 23, runs a spin-off business called SmartFarms, which works on food security and developing food safety systems for urban farming using advanced drone technology and biochemical sensory systems. According to a recent report, more than 30,000 Detroiters don't have access to a full-service grocery store, and 48 percent are considered food insecure.
"We don't tell them which subjects to do – that's why [the labs] are not working on the same thing," explains Young. "We're trying to give student scientists a place to find their way."
The gap that Young noticed for urban students exists also among rural communities, and the problems they face are different. Students in a lab in Polk County, Florida, decided to tackle citrus greening, a bacterial disease that causes citrus fruit to bear bitter-tasting and underdeveloped fruit. The culprit is the Asian psyllid, a pest common to citrus plants. The problem is so pervasive that it's caused a precipitous decline in the industry, which had been a major one in Polk. At Bok Academy in Lake Wales, also in Florida, students are using drones to get an overhead view of the patterns they can detect to better understand which trees to treat and when.
"With the majority of our area dependent on citrus and various other crops, why not get students involved in problem-solving and research that's going to truly make a difference?" says David Lockett, a STEM facilitator at Bok Academy.
To this end, the students have shared their findings with scientists at the University of Florida and a research lab in Colorado.
A young woman who started in ECOTEK as an elementary-school student will now, at age 24, return to run the research arm of the company.
ECOTEK students have also had a slightly larger audience – the United Nations. The Detroit students have traveled to New York since 2013 to share their learnings with international diplomats from countries like Belize, Cuba, and Antigua.
The students' hands-on experience in the lab often inspires them to pursue academic success across the board at school. Young says that graduating students usually receive an average of $150,000 in college scholarships and score an average of 1450 on the SATs and in the 90th percentile on ACT tests.
Young plans to continue his work to develop these scientists, and after having invested "millions" of dollars of his own money, he's now seeing the fruits of his labor come full circle. A young woman who started in ECOTEK as an elementary-school student will now, at age 24, return to run the research arm of the company.
"It was," he says proudly, "a 14-year investment payback."
Cows on a pasture, who, among other mammals, could experience immense suffering from the New World screwworm.
Combining CRISPR genome editing with the natural phenomenon of gene drive allows us to rewrite the genomes of wild organisms. The benefits of saving children from malaria by editing mosquitoes are obvious and much discussed, but humans aren't the only creatures who suffer. If we gain the power to intervene in a natural world "red in tooth and claw," yet decline to use it, are we morally responsible for the animal suffering that we could have prevented?
Given the power to alter the workings of the natural world, are we morally obligated to use it?
The scenario that may redefine our relationship with the natural world begins with fine clothing. You're dressed to the nines for a formal event, but you arrived early, and it's such a beautiful day that you decided to take a stroll by the nearby lake. Suddenly, you hear the sound of splashing and screams. A child is drowning! Will you dive in to save them? Or let them die, and preserve your expensive outfit?
The philosopher Peter Singer posited this scenario to show that we are all terrible human beings. Just about everyone would save the child and ruin the outfit... leading Singer to question why so few of us give equivalent amounts of money to save children on the other side of the world. The Against Malaria Foundation averages one life saved for every $7000.
But despite having a local bias, our moral compasses aren't completely broken. You never even considered letting the child drown because the situation wasn't your fault. That's because the cause of the problem simply isn't relevant: as the one who could intervene, the consequences are on your head. We are morally responsible for intervening in situations we did not create.
There is a critical difference between Singer's original scenario and the one above: in his version, it was a muddy pond. Any adult can rescue a child from a muddy pond, but a lake is different; you can only save the child if you know how to swim. We only become morally responsible when we acquire the power to intervene.
Few would disagree with either of these moral statements, but when they are combined with increasingly powerful technologies, the implications are deeply unsettling. Given the power to alter the workings of the natural world, are we morally obligated to use it? Recent developments suggest we had best determine the answer soon because, technologically, we are learning to swim. What choices will we make?
Gene drive is a natural phenomenon that occurs when a genetic element reliably spreads through a population even though it reduces the reproductive fitness of individual organisms. Nature has evolved many different mechanisms that result in gene drive, so many that it's nearly impossible to find an organism that doesn't have at least one driving element somewhere in its genome. More than half of our own DNA comprises the broken remnants of gene drives, plus a few active copies.
Scientists have long dreamed of harnessing gene drive to block mosquito-borne disease, with little success. Then came CRISPR genome editing, which works by cutting target genes and replacing them with a new sequence. What happens if you replace the original sequence with the edited version and an encoded copy of the CRISPR system? Gene drive.
CRISPR is a molecular scalpel that we can use to cut, and therefore replace, just about any DNA sequence in any cell. Encode the instructions for the CRISPR system adjacent to the new sequence, and genome editing will occur in the reproductive cells of subsequent generations of heterozygotes, always converting the original wild-type version to the new edited version. By ensuring that offspring will all be born of one sex, or by arranging for organisms that inherit two copies of the gene drive to be sterile, it's theoretically possible to cause a population crash.
(Credit: Esvelt)
When my colleagues and I first described this technology in 2014, we initially focused on the imperative for early transparency. Gene drive research is more like civic governance than traditional technology development: you can decline a treatment recommended by your doctor, but you can’t opt out when people change the shared environment. Applying the traditional closeted model of science to gene drive actively denies people a voice in decisions intended to affect them - and reforming scientific incentives for gene drive could be the first step to making all of science faster and safer.
But open gene drive research is clearly aligned with virtually all of our values. It's when technology places our deepest moral beliefs in conflict that we struggle, and learn who we truly are.
Two of our strongest moral beliefs include our reverence for the natural world and our abhorrence of suffering. Yet some natural species inherently cause tremendous suffering. Are we morally obligated to alter or even eradicate them?
To anyone who doubts that the natural world can inflict unimaginable suffering, consider the New World screwworm.
Judging by history, the answer depends on who is doing the suffering. We view the eradication of smallpox as one of our greatest triumphs, clearly demonstrating that we value human lives over the existence of disease-causing microorganisms. The same principle holds today for malaria: few would argue against using gene drive to crash populations of malarial mosquitoes to help eradicate the disease. There are more than 3500 species of mosquitoes, only three of which would be affected, and once malaria is gone, the mosquitoes could be allowed to recover. It would be extremely surprising if African nations decided not to eradicate malaria.
The more interesting question concerns our moral obligations to animals in the state of nature.
To anyone who doubts that the natural world can inflict unimaginable suffering, consider the New World screwworm, Cochyliomyia hominivorax. Female screwworm flies lay their eggs in open wounds, generating maggots that devour healthy tissue, gluttonously burrowing into the flesh of their host until they drop, engorged and sated, to metamorphose. Yet before they fall, the maggots in a wound emit a pheromone attracting new females, thereby acting as both conductors and performers in a macabre parade that consumes the host alive. The pain is utterly excruciating, so much so that infested people often require morphine before doctors can even examine the wound. Worst of all, the New World screwworm specializes in devouring complex mammals.
Every second of every day, hundreds of millions of animals suffer the excruciating agony of being eaten alive. It has been so throughout North and South America for millions of years. Until 2001, when humanity eradicated the last screwworm fly north of Panama using the “sterile insect techniqueâ€. This was not done to protect wild animals or even people, but for economic reasons: the cost of the program was small relative to the immense damage wrought by the screwworm on North American cattle, sheep, and goats. There were no obvious ecological effects. Despite being almost completely unknown even among animal rights activists, the screwworm elimination campaign may well have been one of the greatest triumphs of animal well-being.
Unfortunately, sterile insect technique isn't powerful enough to eradicate the screwworm from South America, where it is more entrenched and protected by the rougher terrain. But gene drive is.
Contrary to news hype, gene drive alone can't cause extinction, but if combined with conventional measures it might be possible to remove targeted species from the wild. For certain species that cause immense suffering, we may be morally obligated to do just that.
(Credit: Esvelt)
South Americans may well decide to eradicate screwworm for the same economic reasons that it was eradicated from North America: the fly inflicts $4 billion in annual damages on struggling rural communities that can least afford it. It need not go extinct, of course; the existence of the sterile insect facility in Panama proves that we can maintain the screwworm indefinitely in captivity on already dead meat.
Yet if for some reason humanity chooses to leave the screwworm as it is - even for upstanding moral reasons, whatever those may be - the knowledge of our responsibility should haunt us.
Tennyson wrote,
Are God and Nature then at strife,
That Nature lends such evil dreams?
So careful of the type she seems,
So careless of the single life.
Evolution by natural selection cares nothing for the single life, nor suffering, nor euphoria, save for their utility in replication. Theoretically, we do. But how much?
[Editor's Note: This story was originally published in May 2018. We are resurfacing archive hits while our staff is on vacation.]